grill-me
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The instructions establish a helpful persona for design review. No malicious override or bypass patterns were detected.\n- [DATA_EXFILTRATION]: The skill does not contain any network-related commands or exfiltration logic.\n- [REMOTE_CODE_EXECUTION]: No remote execution or external package installation patterns are present.\n- [DATA_EXPOSURE]: While the skill permits exploration of the codebase, this is essential for its primary function and does not involve accessing sensitive system-level files or credentials.
Audit Metadata